{"id":"https://openalex.org/W4405183894","doi":"https://doi.org/10.1186/s13321-024-00934-w","title":"Be aware of overfitting by hyperparameter optimization!","display_name":"Be aware of overfitting by hyperparameter optimization!","publication_year":2024,"publication_date":"2024-12-09","ids":{"openalex":"https://openalex.org/W4405183894","doi":"https://doi.org/10.1186/s13321-024-00934-w","pmid":"https://pubmed.ncbi.nlm.nih.gov/39654058"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-024-00934-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00934-w","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00934-w","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00934-w","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067679577","display_name":"Igor V. Tetko","orcid":"https://orcid.org/0000-0002-6855-0012"},"institutions":[{"id":"https://openalex.org/I3018134672","display_name":"Helmholtz Zentrum M\u00fcnchen","ror":"https://ror.org/00cfam450","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672"]},{"id":"https://openalex.org/I4210149356","display_name":"Target (Germany)","ror":"https://ror.org/04kmxp840","country_code":"DE","type":"company","lineage":["https://openalex.org/I1320354487","https://openalex.org/I4210149356"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Igor V. Tetko","raw_affiliation_strings":["BIGCHEM GmbH, Valerystr. 49, 85716, Unterschlei\u00dfheim, Germany. igor.tetko@helmholtz-munich.de","Institute of Structural Biology, Molecular Targets and Therapeutics Center, Helmholtz Munich - Deutsches Forschungszentrum F\u00fcr Gesundheit Und Umwelt (GmbH), 86764, Neuherberg, Germany. igor.tetko@helmholtz-munich.de","Institute of Structural Biology, Molecular Targets and Therapeutics Center, Helmholtz Munich - Deutsches Forschungszentrum F\u00fcr Gesundheit Und Umwelt (GmbH), 86764, Neuherberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BIGCHEM GmbH, Valerystr. 49, 85716, Unterschlei\u00dfheim, Germany. igor.tetko@helmholtz-munich.de","institution_ids":["https://openalex.org/I3018134672"]},{"raw_affiliation_string":"Institute of Structural Biology, Molecular Targets and Therapeutics Center, Helmholtz Munich - Deutsches Forschungszentrum F\u00fcr Gesundheit Und Umwelt (GmbH), 86764, Neuherberg, Germany. igor.tetko@helmholtz-munich.de","institution_ids":["https://openalex.org/I3018134672"]},{"raw_affiliation_string":"Institute of Structural Biology, Molecular Targets and Therapeutics Center, Helmholtz Munich - Deutsches Forschungszentrum F\u00fcr Gesundheit Und Umwelt (GmbH), 86764, Neuherberg, Germany","institution_ids":["https://openalex.org/I3018134672","https://openalex.org/I4210149356"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029204349","display_name":"Ruud van Deursen","orcid":"https://orcid.org/0000-0002-8124-7325"},"institutions":[{"id":"https://openalex.org/I2801043613","display_name":"Firmenich (Switzerland)","ror":"https://ror.org/04d9v0a44","country_code":"CH","type":"company","lineage":["https://openalex.org/I2801043613"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ruud van Deursen","raw_affiliation_strings":["DSM-Firmenich SA, Rue de la Berg\u00e8re 7, Satigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DSM-Firmenich SA, Rue de la Berg\u00e8re 7, Satigny, Switzerland","institution_ids":["https://openalex.org/I2801043613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003838040","display_name":"Guillaume Godin","orcid":"https://orcid.org/0000-0001-9828-386X"},"institutions":[{"id":"https://openalex.org/I2799982174","display_name":"Open Source Drug Discovery","ror":"https://ror.org/05pvypf90","country_code":"IN","type":"healthcare","lineage":["https://openalex.org/I2799351866","https://openalex.org/I2799982174","https://openalex.org/I4210134808","https://openalex.org/I66760702"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Guillaume Godin","raw_affiliation_strings":["Osmo Labs, PBC, 450 E 29th St, New York, USA. guillaume.godin@gmail.com","Osmo Labs, PBC, 450 E 29th St, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osmo Labs, PBC, 450 E 29th St, New York, USA. guillaume.godin@gmail.com","institution_ids":["https://openalex.org/I2799982174"]},{"raw_affiliation_string":"Osmo Labs, PBC, 450 E 29th St, New York, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003838040","https://openalex.org/A5067679577"],"corresponding_institution_ids":["https://openalex.org/I2799982174","https://openalex.org/I3018134672","https://openalex.org/I4210149356"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":4.4513,"has_fulltext":true,"cited_by_count":44,"citation_normalized_percentile":{"value":0.97460148,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"16","issue":"1","first_page":"139","last_page":"139"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9807000160217285,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.9458830952644348},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.9223482608795166},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7228958606719971},{"id":"https://openalex.org/keywords/hyperparameter-optimization","display_name":"Hyperparameter optimization","score":0.6766476631164551},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6497698426246643},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6070411205291748},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5904028415679932},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4258309304714203},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.4112512469291687},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.24598565697669983},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.10214284062385559},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.08189946413040161}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.9458830952644348},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9223482608795166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7228958606719971},{"id":"https://openalex.org/C10485038","wikidata":"https://www.wikidata.org/wiki/Q48996162","display_name":"Hyperparameter optimization","level":3,"score":0.6766476631164551},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6497698426246643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6070411205291748},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5904028415679932},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4258309304714203},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.4112512469291687},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.24598565697669983},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.10214284062385559},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.08189946413040161}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/s13321-024-00934-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00934-w","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00934-w","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:39654058","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39654058","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of cheminformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11629497","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11629497","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11629497/pdf/13321_2024_Article_934.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:c31d859df25a40fe8dd5d9e14a2bce7f","is_oa":false,"landing_page_url":"https://doaj.org/article/c31d859df25a40fe8dd5d9e14a2bce7f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 16, Iss 1, Pp 1-11 (2024)","raw_type":"article"},{"id":"pmh:oai:push-zb.helmholtz-munich.de:72719","is_oa":true,"landing_page_url":"https://push-zb.helmholtz-munich.de/frontdoor.php?source_opus=72719","pdf_url":null,"source":{"id":"https://openalex.org/S7407055352","display_name":"PuSH - Publication Server of Helmholtz Zentrum M\u00fcnchen","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J. Cheminformatics 16:139 (2024)","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1186/s13321-024-00934-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00934-w","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00934-w","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G5178217691","display_name":null,"funder_award_id":"956832","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405183894.pdf","grobid_xml":"https://content.openalex.org/works/W4405183894.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1966441763","https://openalex.org/W1990399577","https://openalex.org/W1992305254","https://openalex.org/W2010611103","https://openalex.org/W2013894207","https://openalex.org/W2022978420","https://openalex.org/W2052260244","https://openalex.org/W2076498053","https://openalex.org/W2089578131","https://openalex.org/W2094836090","https://openalex.org/W2342596260","https://openalex.org/W2883393965","https://openalex.org/W2966357564","https://openalex.org/W2966797369","https://openalex.org/W2968734407","https://openalex.org/W2972498877","https://openalex.org/W2982978720","https://openalex.org/W3030978062","https://openalex.org/W3113282615","https://openalex.org/W3120028903","https://openalex.org/W3159157674","https://openalex.org/W3192495768","https://openalex.org/W4220785481","https://openalex.org/W4285043533","https://openalex.org/W4311001462","https://openalex.org/W4388227674","https://openalex.org/W4391508920","https://openalex.org/W4394624493","https://openalex.org/W4398172073"],"related_works":["https://openalex.org/W2953665647","https://openalex.org/W4281646320","https://openalex.org/W4205712847","https://openalex.org/W3169687406","https://openalex.org/W1974336862","https://openalex.org/W4388119537","https://openalex.org/W4298369531","https://openalex.org/W3014750173","https://openalex.org/W4386295066","https://openalex.org/W4396679425"],"abstract_inverted_index":{"Hyperparameter":[0],"optimization":[1,11,70],"is":[2],"very":[3],"frequently":[4],"employed":[5],"in":[6,20,75],"machine":[7],"learning.":[8],"However,":[9],"an":[10],"of":[12,16,22,121,149,159,174],"a":[13,112,156],"large":[14],"space":[15],"parameters":[17],"could":[18,90],"result":[19,74],"overfitting":[21,81,195],"models.":[23],"In":[24,63],"recent":[25],"studies":[26],"on":[27,117],"solubility":[28,37],"prediction":[29],"the":[30,84,97,107,135,172,180],"authors":[31],"collected":[32],"seven":[33],"thermodynamic":[34],"and":[35,48,60,196],"kinetic":[36],"datasets":[38],"from":[39,194],"different":[40,56],"data":[41,57],"sources.":[42],"They":[43],"used":[44],"state-of-the-art":[45],"graph-based":[46,144],"methods":[47,145],"compared":[49,162,214],"models":[50,188],"developed":[51],"for":[52,146],"each":[53],"dataset":[54],"using":[55,83,93,133,154,178,198],"cleaning":[58],"protocols":[59],"hyperparameter":[61,69],"optimization.":[62],"our":[64],"study":[65],"we":[66,170],"showed":[67,186],"that":[68,128,187,197],"did":[71],"not":[72,168],"always":[73],"better":[76,141],"models,":[77],"possibly":[78],"due":[79],"to":[80,163,215],"when":[82],"same":[85,136,181],"statistical":[86,182],"measures.":[87],"Similar":[88],"results":[89,142,177],"be":[91],"calculated":[92],"pre-set":[94,199],"hyperparameters,":[95],"reducing":[96],"computational":[98],"effort":[99],"by":[100,110,153],"around":[101],"10,000":[102],"times.":[103],"We":[104,126,185],"also":[105],"extended":[106],"previous":[108],"analysis":[109],"adding":[111],"representation":[113],"learning":[114],"method":[115],"based":[116],"Natural":[118],"Language":[119],"Processing":[120],"smiles":[122],"called":[123],"Transformer":[124,138,208],"CNN.":[125],"show":[127],"across":[129],"all":[130],"analyzed":[131],"sets":[132],"exactly":[134,179],"protocol,":[137],"CNN":[139,209],"provided":[140,210],"than":[143],"26":[147],"out":[148],"28":[150],"pairwise":[151],"comparisons":[152],"only":[155],"tiny":[157],"fraction":[158],"time":[160],"as":[161],"other":[164,216],"methods.":[165,218],"Last":[166],"but":[167,204],"least":[169],"stressed":[171],"importance":[173],"comparing":[175],"calculation":[176],"measures.Scientific":[183],"Contribution":[184],"with":[189],"pre-optimized":[190],"hyperparameters":[191,200],"can":[192],"suffer":[193],"yields":[201],"similar":[202],"performances":[203],"four":[205],"orders":[206],"faster.":[207],"significantly":[211],"higher":[212],"accuracy":[213],"investigated":[217]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":27},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-10-10T00:00:00"}